INDEX

Explanations

words related to the process of making something firm or fixed

oai_token-act-pair · gpt-3.5-turbo

words related to solidification or finalization processes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nets

-0.77

mong

-0.71

 Quinn

-0.69

«ĺ

-0.68

LAN

-0.64

pless

-0.64

 Eden

-0.63

meter

-0.62

ney

-0.61

ivan

-0.61

POSITIVE LOGITS

theless

0.81

dyl

0.76

 acceptance

0.73

 dominance

0.72

uate

0.72

Statement

0.71

ulate

0.71

ATIONS

0.69

CLASSIFIED

0.69

ATION

0.68

Activations Density 0.075%

words related to the process of making something firm or fixed

words related to solidification or finalization processes

No Comments

No Known Activations